<tool id="lrn_risk" name="PIMA: LRNRisk" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>isolate classification</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#import re

#for $i in $blast_features_collection:
    #set file_name = $i.file_name
    #set identifier = re.sub('[^\s\w\-\\.]', '_', str($i.element_identifier))
    #if $identifier.lower().startswith('features_amr'):
        #set amr_determinants_input = $identifier
    #else if $identifier.lower().startswith('features_vfdb'):
        #set virulence_factors_input = $identifier
    #end if
    ln -s '$file_name' '$identifier' &&
#end for

python '$__tool_directory__/lrn_risk.py'
--gtdb_file '$gtdb_file'
--virulence_factors_file '$virulence_factors_input'
--amr_determinants_file '$amr_determinants_input'
--blacklist_file '$blacklist_file'
--vf_distribution_file '$vf_distribution_file'
--amr_distribution_file '$amr_distribution_file'
--blacklist_output_file '$blacklist_output_file'
--vfdb_output_file '$vfdb_output_file'
--amr_output_file '$amr_output_file'
]]></command>
    <inputs>
        <param name="gtdb_file" type="data" format="tabular,tsv" label="GTDB-Tk Classify genomes file"/>
        <param name="blast_features_collection" format="tabular,tsv" type="data_collection" collection_type="list" label="Collection BLAST features databases"/>
        <param name="blacklist_file" type="data" format="tabular,tsv" label="File containing blacklisted high-risk virulence factors"/>
        <param name="vf_distribution_file" type="data" format="tabular,tsv" label="File containing virulence factor distribution"/>
        <param name="amr_distribution_file" type="data" format="tabular,tsv" label="File containing AMR determinant distribution"/>
    </inputs>
    <outputs>
        <data name="blacklist_output_file" format="tsv" label="${tool.name} on ${on_string} (blacklist)"/>
        <data name="vfdb_output_file" format="tsv" label="${tool.name} on ${on_string} (VFDB)"/>
        <data name="amr_output_file" format="tsv" label="${tool.name} on ${on_string} (AMR)"/>
    </outputs>
    <tests>
        <test>
            <param name="gtdb_file" value="gtdb.tsv" ftype="tsv"/>
            <param name="blast_features_collection">
                <collection type="list">
                    <element name="FEATURES_AMR_database_2023_02_02.fasta" value="FEATURES_AMR_database_2023_02_02.tsv"/>
                    <element name="FEATURES_incompatibility_groups_database_2023_01_01.fasta" value="FEATURES_incompatibility_groups_database_2023_01_01.tsv"/>
                    <element name="FEATURES_vfdb_core_database_2023_03_30.fasta" value="FEATURES_vfdb_core_database_2023_03_30.tsv"/>
                </collection>
            </param>
            <param name="blacklist_file" value="blacklist.tsv" ftype="tsv"/>
            <param name="vf_distribution_file" value="vf_distribution.tsv" ftype="tsv"/>
            <param name="amr_distribution_file" value="amr_distribution.tsv" ftype="tsv"/>
            <output name="blacklist_output_file" value="blacklist_output.tsv" ftype="tsv"/>
            <output name="vfdb_output_file" value="vfdb_output.tsv" ftype="tsv"/>
            <output name="amr_output_file" value="amr_output.tsv" ftype="tsv"/>
        </test>
    </tests>
    <help>
**What it does**

Classifies isolates into "high risk" and "unlikely high risk" and provides information about prevalence of a given virulence
gene among all publicly available genome of a given species and prevalence of a given antimicrobial resistance gene among all
publicly available genomes of a given species. 
    </help>
    <expand macro="citations"/>
</tool>